#!/usr/bin/env python """ Merge a CPT LoRA adapter into its base model and save a plain 16-bit model folder. Needed when the CPT run was uploaded as an ADAPTER (adapter_config.json + adapter_model.safetensors) rather than as merged weights. After merging, the folder loads like any ordinary model, so sft_gemma4_mcq.py can train on it with no changes: python merge_adapter.py --adapter ovinduG/gemma4-e4b-sinhala-cpt-d3-c3ucsc \ --out /workspace/models/cpt_d3c3_merged python sft_gemma4_mcq.py --train sft_train.jsonl --val sft_val.jsonl \ --model /workspace/models/cpt_d3c3_merged --out /workspace/outputs/mcq_sft_cpt_d3c3 Why merge instead of training the adapter directly: loading the adapter gives a PeftModel, and the SFT script then adds a SECOND LoRA on top. Saving/merging that stack is error-prone, and the parameter count for the 8B rule stops being obvious. Merging folds the CPT LoRA into the existing weight matrices, so the result is still ~7.996B parameters. Needs the GPU free (stop any training job first) and ~16 GB of free disk for the output. """ import argparse import json import os import struct import sys from pathlib import Path os.environ.setdefault("HF_HUB_ENABLE_HF_TRANSFER", "1") LIMIT = 8_000_000_000 # shared-task parameter cap def adapter_info(src): """Print what we are about to merge: base model and LoRA rank, read from adapter_config.json.""" cfg = None p = Path(src) / "adapter_config.json" if p.exists(): cfg = json.loads(p.read_text(encoding="utf-8")) else: try: from huggingface_hub import hf_hub_download cfg = json.loads(Path(hf_hub_download(src, "adapter_config.json")).read_text(encoding="utf-8")) except Exception as e: # noqa: BLE001 print(f"[warn] could not read adapter_config.json ({type(e).__name__}: {e}); " "if this is already a merged model you do not need this script") return None print(f"[adapter] base model : {cfg.get('base_model_name_or_path')}") print(f"[adapter] LoRA r={cfg.get('r')} alpha={cfg.get('lora_alpha')} " f"rslora={cfg.get('use_rslora')} targets={cfg.get('target_modules')}") return cfg def count_params(folder): """Sum parameter counts from safetensors headers (no need to load the weights).""" total = 0 for f in sorted(Path(folder).glob("*.safetensors")): with open(f, "rb") as fh: n = struct.unpack(" {'OK, under 8B' if n <= LIMIT else 'OVER THE 8B LIMIT'}") return adapter_info(args.adapter) from unsloth import FastModel # imported late, as in the other scripts print(f"[load] {args.adapter} (base weights download on first use, ~16 GB)") model, tok = FastModel.from_pretrained(model_name=args.adapter, max_seq_length=args.max_seq_length, dtype=None, load_in_4bit=False) print(f"[merge] writing merged 16-bit model to {args.out}") model.save_pretrained_merged(args.out, tok, save_method="merged_16bit") files = sorted(p.name for p in Path(args.out).iterdir()) print(f"[done] {len(files)} files: {', '.join(files)}") n = count_params(args.out) print(f"[check] parameters: {n:,} -> {'OK, under 8B' if n <= LIMIT else 'OVER THE 8B LIMIT'}") for need in ["config.json", "tokenizer.json", "tokenizer_config.json"]: if need not in files: print(f"[warn] {need} is missing from {args.out}; loading it may fail") if not any(f.endswith(".safetensors") for f in files): sys.exit("no safetensors were written: the merge failed") if __name__ == "__main__": main()